A policy iteration algorithm of adaptive dynamic programming（ADP） is developed to solve the optimal tracking control for a class of discrete-time chaotic systems. By system transformations, the optimal tracking prob...
详细信息
A policy iteration algorithm of adaptive dynamic programming（ADP） is developed to solve the optimal tracking control for a class of discrete-time chaotic systems. By system transformations, the optimal tracking problem is transformed into an optimal regulation one. The policy iteration algorithm for discrete-time chaotic systems is first described. Then,the convergence and admissibility properties of the developed policy iteration algorithm are presented, which show that the transformed chaotic system can be stabilized under an arbitrary iterative control law and the iterative performance index function simultaneously converges to the optimum. By implementing the policy iteration algorithm via neural networks,the developed optimal tracking control scheme for chaotic systems is verified by a simulation.
This paper presents a method for planar motion measurement of a swimming multi-joint robotic fish. The motion of the robotic fish is captured via image sequences and a proposed tracking scheme is employed to continuou...
详细信息
This paper presents a method for planar motion measurement of a swimming multi-joint robotic fish. The motion of the robotic fish is captured via image sequences and a proposed tracking scheme is employed to continuously detect and track the robotic fish. The tracking scheme initially acquires a rough scope of the robotic fish and thereafter precisely locates it. Historical motion information is utilized to determine the rough scope, which can speed up the tracking process and avoid possible ambient interference. A combination of adaptive bilateral filtering and k-means clustering is then applied to segment out color markers accurately. The pose of the robotic fish is calculated in accordance with the centers of these markers. Further, we address the problem of time synchronization between the on-board motion controlsystem of the robotic fish and the motion measurement system. To the best of our knowledge, this problem has not been tackled in previous research on robotic fish. With information about both the multi-link structure and motion law of the robotic fish, we convert the problem to a nonlinear optimization problem, which we then solve using the particle swarm optimization(PSO) algorithm. Further, smoothing splines are adopted to fit curves of poses versus time, in order to obtain a continuous motion state and alleviate the impact of noise. Velocity is acquired via a temporal derivative operation. The results of experiments conducted verify the efficacy of the proposed method.
This paper investigates the performance of the dual mode, namely flipper mode and central pattern generator(CPG) mode, for controlling the depth of a gliding robotic dolphin. Subsequent to considering the errors in dy...
详细信息
This paper investigates the performance of the dual mode, namely flipper mode and central pattern generator(CPG) mode, for controlling the depth of a gliding robotic dolphin. Subsequent to considering the errors in dynamic models, we propose a depth controlsystem that combines the line-of-sight(LOS)method with an adaptive control approach(ACA) to deal with uncertainties in the model parameters. First,we establish a full-state dynamic model to conduct simulations and optimize the parameters used in later aquatic experiments. Then, we use the LOS method to transform the control target from the depth to the pitch angle and employ the ACA to calculate the control signal. In particular, we optimize the ACA’s control parameters using simulations based on our dynamic model. Finally, our simulated and experimental results demonstrate not only that we can successfully control the robotic dolphin’s depth, but also that its performance was better than that of the CPG-based control, thus indicating that we can achieve three-dimensional motion by combining flipper-based and CPG-based control. The results of this study suggest valuable ideas for practical applications of gliding robotic dolphins.
This paper mainly focuses on designing a sliding mode boundary controller for a single flexible-link manipulator based on adaptive radial basis function （RBF） neural network. The flexible manipulator in this paper i...
详细信息
This paper mainly focuses on designing a sliding mode boundary controller for a single flexible-link manipulator based on adaptive radial basis function （RBF） neural network. The flexible manipulator in this paper is considered to be an Euler-Bernoulli beam. We first obtain a partial differential equation （PDE） model of single-link flexible manipulator by using Hamiltons approach. To improve the control robustness, the system uncertainties including modeling uncertainties and external disturbances are compensated by an adaptive neural approximator. Then, a sliding mode control method is designed to drive the joint to a desired position and rapidly suppress vibration on the beam. The stability of the closed-loop system is validated by using Lyapunov＇s method based on infinite dimensional model, avoiding problems such as control spillovers caused by traditional finite dimensional truncated models. This novel controller only requires measuring the boundary information, which facilitates implementation in engineering practice. Favorable performance of the closed-loop system is demonstrated by numerical simulations.
Tremendous amount of data are being generated and saved in many complex engineering and social systems every *** is significant and feasible to utilize the big data to make better decisions by machine learning techniq...
详细信息
Tremendous amount of data are being generated and saved in many complex engineering and social systems every *** is significant and feasible to utilize the big data to make better decisions by machine learning techniques. In this paper, we focus on batch reinforcement learning(RL) algorithms for discounted Markov decision processes(MDPs) with large discrete or continuous state spaces, aiming to learn the best possible policy given a fixed amount of training data. The batch RL algorithms with handcrafted feature representations work well for low-dimensional MDPs. However, for many real-world RL tasks which often involve high-dimensional state spaces, it is difficult and even infeasible to use feature engineering methods to design features for value function approximation. To cope with high-dimensional RL problems, the desire to obtain data-driven features has led to a lot of works in incorporating feature selection and feature learning into traditional batch RL algorithms. In this paper, we provide a comprehensive survey on automatic feature selection and unsupervised feature learning for high-dimensional batch RL. Moreover, we present recent theoretical developments on applying statistical learning to establish finite-sample error bounds for batch RL algorithms based on weighted Lpnorms. Finally, we derive some future directions in the research of RL algorithms, theories and applications.
Background: Evidence linking fine particulate matter (PM2.5) constituents to childhood attention deficit hyperactivity disorder (ADHD) was limited. Objectives: To investigate the individual and joint effects of exposu...
详细信息
Group behavior forecasting is an emergent re- search and application field in social computing. Most of the existing group behavior forecasting methods have heavily re- lied on structured data which is usually hard to...
详细信息
Group behavior forecasting is an emergent re- search and application field in social computing. Most of the existing group behavior forecasting methods have heavily re- lied on structured data which is usually hard to obtain. To ease the heavy reliance on structured data, in this paper, we pro- pose a computational approach based on the recognition of multiple plans/intentions underlying group behavior. We fur- ther conduct human experiment to empirically evaluate the effectiveness of our proposed approach.
This paper proposes a new biologically inspired emotional attention model to expand existing visual attention models by considering emotional impact on *** our work,we combine color emotion activity and emotional arou...
详细信息
ISBN:
(纸本)9781467349970
This paper proposes a new biologically inspired emotional attention model to expand existing visual attention models by considering emotional impact on *** our work,we combine color emotion activity and emotional arousal with visual spatial *** the experiments,an affective picture dataset and an eye-tracking dataset are used to test our proposed *** results show that the performance of the emotional attention model is promising.
暂无评论